Detection of Mild Cognitive Impairment Using Convolutional Neural Network: Temporal-Feature Maps of Functional Near-Infrared Spectroscopy

Detection of cognitive load during computer-aided education using infrared sensors

Technology integration in modern education has transformed traditional teaching-learning methods, but maintaining student attentiveness during computer-aided activities remains challenging. Neuroimaging advancements provide valuable insights into cognitive processes. This study measures cognitive load during computer-aided education. We have collected functional near-infrared spectroscopy (fNIRS) brain signals while subjects perform mental tasks and rest. Three datasets have been considered to evaluate the performance of the proposed model. The first two datasets are open-access, and we prepare the third dataset by collecting fNIRS brain signals from 14 healthy subjects. Two feature extraction techniques are proposed: manual and automatic based on wavelet scattering transform (WST). A one dimensional convolutional neural network (1D CNN) is also proposed to automatically extract features through feature engineering and classification. For comparison, four machine learning classifiers, linear discriminant analysis (LDA), Naive Bayes (NB), k-nearest neighbors (KNN) and support vector machine (SVM), are also considered. Classification performance is evaluated using accuracy, precision, recall and F1-score across all datasets. Computational cost, i.e., the CPU time and memory utilization for extracting the features and testing the classifiers, is also evaluated. The results suggest that when considering four classifiers across three datasets and comparing among the manual and the WST-based feature extraction methods, the average performance of 1D CNN is superior in terms of classification accuracy (1.16 times higher), precision (1.10 times higher), recall (1.10 times higher) and F1-score (1.09 times higher). However, the CPU time and memory utilization for 1D CNN are significantly higher, 10.09 and 14.70 times, respectively. In comparison to four state-of-the-art deep learning models, the proposed 1D CNN also shows best classification accuracy (92.99%). The analysis of the results shows that identifying cognitive load, SVM with Gaussian kernel function on WST based methods, provides satisfactory classification performance with significantly less CPU time and memory utilization.

Brain remodeling in stroke patients: A comprehensive review of mechanistic and neuroimaging studies

Stroke-induced brain remodeling involves a complex interplay of neurovascular components, including endothelial cells, microglia, astrocytes, and pericytes, which collectively contribute to the restoration of brain function. These processes are crucial for repairing the blood-brain barrier, regulating inflammation, and promoting neurogenesis. This review examines the mechanisms underlying brain remodeling and the role of advanced neuroimaging techniques-such as functional MRI (fMRI), positron emission tomography (PET), functional near-infrared spectroscopy (fNIRS), and functional ultrasound (fUS)-in assessing these changes. We also discuss various therapeutic approaches aimed at enhancing brain remodeling, including pharmacological agents, stem cell therapy, and rehabilitation strategies that target neurovascular repair and functional recovery. Despite significant progress, challenges remain in translating imaging insights into effective treatments. Future research should focus on integrating multiple imaging modalities to provide a comprehensive view of neurovascular changes and refining therapeutic interventions to optimize recovery and functional outcomes in stroke patients.

Comparative study of brain functional imaging of brain in patients with mild to moderate Alzheimer's disease based on functional near infrared spectroscopy

OBJECTIVE

Based on the near-infrared functional brain imaging system, this research studied the hemoglobin concentration signal in resting state and task state. The purpose of this research was to analyze the activated brain regions and functional connections by exploring the changes in hemoglobin concentration and the differences in brain network functional connections between healthy people and mild to moderate AD patients. So as to identify the cognitive dysfunction of patients at an early stage. By accurately locating the area of cognitive impairment in patients, it provides a basis for precise neural regulation of physical therapy.

METHODS

Patients who came to our hospital from January 2022 to December 2022 were recruited and selected according to the exclusion criteria. After receiving their informed consent, MMSE scale examination and near-infrared brain function imaging examination were performed in a relatively quiet environment.

RESULT

A total of 24 subjects were included in this study, including 7 in the control group (age: 72.57 ± 7.19) and 17 (age: 76.88 ± 9.29) in the AD group. The average cognitive scores were (28.00 ± 1.16), (19.24 ± 4.89), respectively. There were no statistically significant differences in gender, years of education, age, and past medical history between the AD group and the control group (P > 0.05). In the verbal fluency test (VFT) task, there was a significant difference in the activation values of the two groups in channels 01, 06, 07, 09, 13, 14, 15, 16, 19, 21, 22, 23, 27, 29, 31, 35, 38, 40, 43, 44, 45, 51, and 52II (p < 0.05), and the activation values of the normal group were greater than those of the AD group. There was a significant difference in the mean oxygenated hemoglobin concentration in channels 01, 07, 15, 16, 21, 22, 23, 31, 35, 40, 41, 44, and 48 (p < 0.05), and the average oxygenated hemoglobin concentration in the AD group was lower than that in the normal group. There was no significant difference in activation speed between the two groups. In the resting state, the number of total network edges, DLPFC-L to PreM and SMC-L, DLPFC-L to FEF-L, DLPFC-L to DLPFC-L, FPA-L to PreM and SMC-L, FPA-L to FPA-L, FPA-R to FPA-L, DLPFC-L to DLPFC-R, FEF-R to PreM and There was a statistically significant difference in the number of network edges in SMC-L (p < 0.05). Among the different groups, the number of network edges in the AD group was smaller than that in the normal group. Correlation analysis showed that T14, T31, T16, T23, T27, M16, M22, M41 (T: represents activation value, M: represents mean hemoglobin concentration, and number represents channel number). There was a positive correlation between the total number of network edges, DLPFC-L to PreM and SMC-L, DLPFC-L to DLPFC-L, FPA-L to PreM and SMC-L, FPA-L to FPA-L, DLPFC-L to DLPFC-R, FEF-R to PreM and SMC-L, and MMSE scores (p < 0.05).

DISCUSSION

In this study, we found hemodynamic changes in the prefrontal lobes of AD patients under the VFT task, and the decrease in the functional connectivity of the prefrontal brain network in AD patients in the resting state, and these changes were associated with cognitive decline in patients. Our findings suggest that fNIRS may be used as a tool for future clinical screening for cognitive impairment, and may also be used to develop personalized preventive measures and treatment plans through accurate assessment.

Screening tools for subjective cognitive decline and mild cognitive impairment based on task-state prefrontal functional connectivity: a functional near-infrared spectroscopy study

BACKGROUND

Subjective cognitive decline (SCD) and mild cognitive impairment (MCI) carry the risk of progression to dementia, and accurate screening methods for these conditions are urgently needed. Studies have suggested the potential ability of functional near-infrared spectroscopy (fNIRS) to identify MCI and SCD. The present fNIRS study aimed to develop an early screening method for SCD and MCI based on activated prefrontal functional connectivity (FC) during the performance of cognitive scales and subject-wise cross-validation via machine learning.

METHODS

Activated prefrontal FC data measured by fNIRS were collected from 55 normal controls, 80 SCD patients, and 111 MCI patients. Differences in FC were analyzed among the groups, and FC strength and cognitive scale performance were extracted as features to build classification and predictive models through machine learning. Model performance was assessed based on accuracy, specificity, sensitivity, and area under the curve (AUC) with 95 % confidence interval (CI) values.

RESULTS

Statistical analysis revealed a trend toward more impaired prefrontal FC with declining cognitive function. Prediction models were built by combining features of prefrontal FC and cognitive scale performance and applying machine learning models, The models showed generally satisfactory abilities to differentiate among the three groups, especially those employing linear discriminant analysis, logistic regression, and support vector machine. Accuracies of 92.0 % for MCI vs. NC, 80.0 % for MCI vs. SCD, and 76.1 % for SCD vs. NC were achieved, and the highest AUC values were 97.0 % (95 % CI: 94.6 %-99.3 %) for MCI vs. NC, 87.0 % (95 % CI: 81.5 %-92.5 %) for MCI vs. SCD, and 79.2 % (95 % CI: 71.0 %-87.3 %) for SCD vs. NC.

CONCLUSION

The developed screening method based on fNIRS and machine learning has the potential to predict early-stage cognitive impairment based on prefrontal FC data collected during cognitive scale-induced activation.

Identification of functional near-infrared spectroscopy for older adults with mild cognitive impairment: a systematic review

Objective

Mild cognitive impairment (MCI), a common state of cognitive impairment without significant impairment in daily functioning among older adults, is mainly identified using various neuropsychological tests, clinical interviews, and collateral history with some subjective interferences. This systematic review aimed to investigate the functional near-infrared spectroscopy (fNIRS) features of older adults with MCI compared with those with normal cognitive function to assist in the diagnosis of MCI.

Methods

A literature search was conducted in electronic databases, including PubMed, Web of Science, Embase, and Cochrane Library, up to June 15, 2024. The data on article information (first author and year of publication), participant characteristics, task paradigms, regions of interest (ROIs), fNIRS device attributes, and results related to cerebral oxygenation and hemodynamics were extracted.

Results

Finally, 34 relevant studies were identified, involving 1033 patients with MCI and 1107 age-, sex-, and education-matched controls with normal cognitive function. We found that the studies frequently used working memory-related task paradigms and resting-state measurements. Also, the prefrontal cortex was a primary ROI, and the changes in oxygenated hemoglobin concentration were the most basic research attributes used to derive measures such as functional connectivity (FC), FC variability, slope, and other parameters. However, ROI activation levels differed inconsistently between patients with MCI and individuals with normal cognition across studies. In general, the activation levels in the ROI of MCI patients may be higher than, lower than, or comparable to those in the normal control group.

Conclusion

Research on fNIRS in elderly patients with MCI aims to provide an objective marker for MCI diagnosis. The current findings are mixed. However, these differences can be partly explained with the theoretical support from the interaction of cognitive load theory and scaffolding theory of aging and cognition, taking into account factors such as unspecified MCI subtypes, task difficulty, task design, monitoring duration, and population characteristics. Therefore, future studies should consider definite MCI subtypes, strict and well-designed paradigms, long-term monitoring, and large sample sizes to obtain the most consistent results, thereby providing objective references for the clinical diagnosis of MCI in elderly patients.

Food properties modulate activities in posterior parietal and visual cortex during chewing

Cross-modal interactions between sensory modalities may be necessary for recognition of chewing food by the invisible oral cavity to avoid damaging the tongue and/or oral mucosa. The present study used functional near-infrared spectroscopy to investigate whether the food properties hardness and size influence activities in the posterior parietal cortex and visual cortex during chewing performance in healthy individuals. It was found that an increase in food hardness enhanced both posterior parietal cortex and visual cortex activities, while an increase in food size enhanced activities in the same regions. These findings suggested a quantitative relationship of oral food properties with activities in the brain regions responsible for object recognition and visuospatial processing. It is thus concluded that heightened neural activities in the posterior parietal cortex and visual area reflect an increased demand for cross-modal representation of food properties related to chewing.

Brain Activation During Motor Preparation and Execution in Patients with Mild Cognitive Impairment: An fNIRS Study

Objectives: This study aimed to investigate how motor preparation impacted brain activation in individuals with differing cognitive statuses. Methods: We investigated the cortical activation pattern of 57 individuals with mild cognitive impairment (MCI) and 67 healthy controls (HCs) using functional near-infrared spectroscopy (fNIRS) during prepared walking (PW) and single walking (SW) tasks. The study focused on assessing brain activity in four regions of interest (ROIs): the prefrontal cortex (PFC), primary motor cortex, secondary motor cortex, and parietal lobe. Additionally, we examined the behavioral performance-gait speed-during the tasks, analyzed variations in cortical activation intensity, and conducted correlation analyses between Montreal Cognitive Assessment (MoCA) scores, gait speed, and oxygenation levels. Results: There was no significant difference in gait speed between patients with MCI and HCs. The MCI group exhibited lower activation in the primary motor cortex, secondary motor cortex, and parietal regions compared to HCs during the motor execution stage of PW (q < 0.05, FDR-corrected). Additionally, activation in the primary (r = 0.23, p = 0.02) and secondary motor cortices (r = 0.19, p = 0.04) during the motor execution stage of PW correlated significantly with MoCA scores. Furthermore, brain activity in the PFC (r = 0.22, p = 0.02), primary motor cortex (r = 0.22, p = 0.01), secondary motor cortex (r = 0.20, p = 0.02), and parietal lobe (r = 0.19, p = 0.03) during the motor preparation stage of gait was positively correlated with gait speed. Conclusions: Our results revealed that preparing for motor tasks modulated the neural activation patterns of patients with MCI and HCs without affecting their behavioral performance.

Brain compensatory activation during Stroop task in patients with mild cognitive impairment: a functional near-infrared spectroscopy study

Purpose

This study investigated the disparities in brain activation patterns during the Stroop task among individuals with mild cognitive impairment (MCI) and those without any cognitive impairments (healthy controls, HCs) using functional near-infrared spectroscopy (fNIRS).

Methods

We analyzed the cortical activation patterns of 73 patients with MCI and 63 HC individuals as they completed the Stroop task, employing fNIRS. The regions of interest (ROIs) included the dorsal prefrontal cortex (dPFC), ventrolateral prefrontal cortex (VLPFC), and parietal lobe (PL). The Stroop task is divided into early stage (0-15 s) and late stage (15-30 s). We also measured participants' behavior during the Stroop task, analyzed variations in cortical activation intensity at different experiment stages, and performed correlation analysis between Montreal Cognitive Assessment (MoCA) scores, Stroop performance, and oxygenation levels.

Results

Our analysis revealed that individuals with MCI and HC demonstrated elevated cortical activation in the dPFC, VLPFC, and PL areas while performing the Stroop task (q < 0.05, FDR-corrected). The MCI group displayed longer response latencies compared to the HC group while demonstrating comparable accuracy performance across both congruent and incongruent Stroop trials. The MCI group showed compensatory activation in the VLPFC, and PL regions compared to the HC group during the late stage of the Stroop task (q < 0.05, FDR-corrected). Correlational analysis revealed a negative association between MoCA scores and oxygenation levels in the dPFC, VLPFC, and PL regions during the late stage of the Stroop task (p < 0.05). However, no correlation was found with behavioral performance.

Conclusion

Mild cognitive impairment patients demonstrated effective compensation for their cognitive impairments at a partial behavioral level by engaging compensatory activation in the prefrontal, and parietal regions while performing the Stroop task.

Resting-State Brain Network Characteristics Related to Mild Cognitive Impairment: A Preliminary fNIRS Proof-of-Concept Study

BACKGROUND

This study investigates the reliability of functional near-infrared spectroscopy (fNIRS) in detecting resting-state brain network characteristics in patients with mild cognitive impairment (MCI), focusing on static resting-state functional connectivity (sRSFC) and dynamic resting-state functional connectivity (dRSFC) patterns in MCI patients and healthy controls (HCs) without cognitive impairment.

METHODS

A total of 89 MCI patients and 83 HCs were characterized using neuropsychological scales. Subject sRSFC strength and dRSFC variability coefficients were evaluated via fNIRS. The study evaluated the feasibility of using fNIRS to measure these connectivity metrics and compared resting-state brain network characteristics between the two groups. Correlations with Montreal Cognitive Assessment (MoCA) scores were also explored.

RESULTS

sRSFC strength in homologous brain networks was significantly lower than in heterologous networks (p < 0.05). A significant negative correlation was also observed between sRSFC strength and dRSFC variability at both the group and individual levels (p < 0.001). While sRSFC strength did not differentiate between MCI patients and HCs, the dRSFC variability between the dorsal attention network (DAN) and default mode network (DMN), and between the ventral attention network (VAN) and visual network (VIS), emerged as sensitive biomarkers after false discovery rate correction (p < 0.05). No significant correlation was found between MoCA scores and connectivity measures.

CONCLUSIONS

fNIRS can be used to study resting-state brain networks, with dRSFC variability being more sensitive than sRSFC strength for discriminating between MCI patients and HCs. The DAN-DMN and VAN-VIS regions were found to be particularly useful for the identification of dRSFC differences between the two groups.

CLINICAL TRIAL REGISTRATION

ChiCTR2200057281, registered on 6 March, 2022; https://www.chictr.org.cn/showproj.html?proj=133808.

Evaluating the impact of boxing on prefrontal cortex activation and cognitive performance: A pilot study using fNIRS technology and the Stroop test

This research sets out to investigate the differences in hemoglobin concentration occurring in the prefrontal cortex (PFC) during the administration of the Stroop test in active amateur boxers and to compare the obtained data regarding chronic traumatic brain injury with those of healthy individuals. The research was conducted at the Atatürk University Neuropsychology Laboratory. Participants consisted of 6 male boxers, aged 19.66 ± 2.94 years, who had been actively boxing for 7.5 ± 3.8 years and had received at least high school level education, with right-hand dominance, and 8 healthy males, aged 19.62 ± 1.18 years, who had not engaged in any combat sports. fNIRS recordings were taken over the Prefrontal Cortex (PFC) while Stroop test stimuli were presented to the participants in a block design. The data were analyzed using the JASP program. Mann-Whitney U test was applied to evaluate the differences between groups in Stroop test data. The activation levels on the prefrontal cortex during the test were evaluated using the Repeated Measures ANOVA test. A significance level of p <0.05 was accepted for the analyses. In conclusion, compared to the control group, boxers demonstrated a significantly higher level of cerebral activation in the right dlPFC/vlPFC regions during the congruent task and in the right dmPFC as well as the left dmPFC/vmPFC/OFC regions during the incongruent task in the Stroop test. When the Stroop test results of the participants were evaluated between groups, it was found that although statistically insignificant compared to healthy subjects, boxers generally exhibited failure. In conclusion, it was found that boxers exhibit higher neural activation responses and lower cognitive performance during neurophysiological testing compared to healthy controls. These two conditions are thought to be interconnected and are considered to result from neural inefficiency.

Cross-modal representation of chewing food in posterior parietal and visual cortex

Even though the oral cavity is not visible, food chewing can be performed without damaging the tongue, oral mucosa, or other intraoral parts, with cross-modal perception of chewing possibly critical for appropriate recognition of its performance. This study was conducted to clarify the relationship of chewing food cross-modal perception with cortex activities based on examinations of the posterior parietal cortex (PPC) and visual cortex during chewing in comparison with sham chewing without food, imaginary chewing, and rest using functional near-infrared spectroscopy. Additionally, the effects of a deafferent tongue dorsum on PPC/visual cortex activities during chewing performance were examined. The results showed that chewing food increased activity in the PPC/visual cortex as compared with imaginary chewing, sham chewing without food, and rest. Nevertheless, those activities were not significantly different during imaginary chewing or sham chewing without food as compared with rest. Moreover, subjects with a deafferent tongue dorsum showed reduced PPC/visual cortex activities during chewing food performance. These findings suggest that chewing of food involves cross-modal recognition, while an oral somatosensory deficit may modulate such cross-modal activities.

Study of the role of leukocyte telomere length-related lncRNA NBR2 in Alzheimer's disease

Alzheimer's Syndrome (AD) is a neurodegenerative disease that is prevalent in middle-aged and elderly people. As the disease progresses, patients gradually lose the ability to take care of themselves, which brings a heavy burden to the family. There is a link between leukocyte telomere length (LTL) and cognitive ability. To search for possible pathogenic mechanisms and potential therapeutic agents, we demonstrated a causal link between LTL and AD using Mendelian randomization analysis (MR). The expression of the target gene NBR2 and the downstream mRNA GJA1 and GJA1-related genes, pathway enrichment, and association with immune cells were further explored. Using the gene cluster-drug target interaction network, we obtained potential therapeutic drugs. Our study provides evidence for a causal link between AD and LTL, suggesting medicines that may treat and alleviate AD symptoms.

Mild cognitive impairment prediction based on multi-stream convolutional neural networks

BACKGROUND

Mild cognitive impairment (MCI) is the transition stage between the cognitive decline expected in normal aging and more severe cognitive decline such as dementia. The early diagnosis of MCI plays an important role in human healthcare. Current methods of MCI detection include cognitive tests to screen for executive function impairments, possibly followed by neuroimaging tests. However, these methods are expensive and time-consuming. Several studies have demonstrated that MCI and dementia can be detected by machine learning technologies from different modality data. This study proposes a multi-stream convolutional neural network (MCNN) model to predict MCI from face videos.

RESULTS

The total effective data are 48 facial videos from 45 participants, including 35 videos from normal cognitive participants and 13 videos from MCI participants. The videos are divided into several segments. Then, the MCNN captures the latent facial spatial features and facial dynamic features of each segment and classifies the segment as MCI or normal. Finally, the aggregation stage produces the final detection results of the input video. We evaluate 27 MCNN model combinations including three ResNet architectures, three optimizers, and three activation functions. The experimental results showed that the ResNet-50 backbone with Swish activation function and Ranger optimizer produces the best results with an F1-score of 89% at the segment level. However, the ResNet-18 backbone with Swish and Ranger achieves the F1-score of 100% at the participant level.

CONCLUSIONS

This study presents an efficient new method for predicting MCI from facial videos. Studies have shown that MCI can be detected from facial videos, and facial data can be used as a biomarker for MCI. This approach is very promising for developing accurate models for screening MCI through facial data. It demonstrates that automated, non-invasive, and inexpensive MCI screening methods are feasible and do not require highly subjective paper-and-pencil questionnaires. Evaluation of 27 model combinations also found that ResNet-50 with Swish is more stable for different optimizers. Such results provide directions for hyperparameter tuning to further improve MCI predictions.

Real-time motion artifact suppression using convolution neural networks with penalty in fNIRS

Introduction

Removing motion artifacts (MAs) from functional near-infrared spectroscopy (fNIRS) signals is crucial in practical applications, but a standard procedure is not available yet. Artificial neural networks have found applications in diverse domains, such as voice and image processing, while their utility in signal processing remains limited.

Method

In this work, we introduce an innovative neural network-based approach for online fNIRS signals processing, tailored to individual subjects and requiring minimal prior experimental data. Specifically, this approach employs one-dimensional convolutional neural networks with a penalty network (1DCNNwP), incorporating a moving window and an input data augmentation procedure. In the training process, the neural network is fed with simulated data derived from the balloon model for simulation validation and semi-simulated data for experimental validation, respectively.

Results

Visual validation underscores 1DCNNwP's capacity to effectively suppress MAs. Quantitative analysis reveals a remarkable improvement in signal-to-noise ratio by over 11.08 dB, surpassing the existing methods, including the spline-interpolation, wavelet-based, temporal derivative distribution repair with a 1 s moving window, and spline Savitzky-Goaly methods. Contrast-to-noise ratio (CNR) analysis further demonstrated 1DCNNwP's ability to restore or enhance CNRs for motionless signals. In the experiments of eight subjects, our method significantly outperformed the other approaches (except offline TDDR, t < -3.82, p < 0.01). With an average signal processing time of 0.53 ms per sample, 1DCNNwP exhibited strong potential for real-time fNIRS data processing.

Discussion

This novel univariate approach for fNIRS signal processing presents a promising avenue that requires minimal prior experimental data and adapts seamlessly to varying experimental paradigms.

Diagnostic machine learning applications on clinical populations using functional near infrared spectroscopy: a review

Functional near-infrared spectroscopy (fNIRS) and its interaction with machine learning (ML) is a popular research topic for the diagnostic classification of clinical disorders due to the lack of robust and objective biomarkers. This review provides an overview of research on psychiatric diseases by using fNIRS and ML. Article search was carried out and 45 studies were evaluated by considering their sample sizes, used features, ML methodology, and reported accuracy. To our best knowledge, this is the first review that reports diagnostic ML applications using fNIRS. We found that there has been an increasing trend to perform ML applications on fNIRS-based biomarker research since 2010. The most studied populations are schizophrenia (n = 12), attention deficit and hyperactivity disorder (n = 7), and autism spectrum disorder (n = 6) are the most studied populations. There is a significant negative correlation between sample size (>21) and accuracy values. Support vector machine (SVM) and deep learning (DL) approaches were the most popular classifier approaches (SVM = 20) (DL = 10). Eight of these studies recruited a number of participants more than 100 for classification. Concentration changes in oxy-hemoglobin (ΔHbO) based features were used more than concentration changes in deoxy-hemoglobin (ΔHb) based ones and the most popular ΔHbO-based features were mean ΔHbO (n = 11) and ΔHbO-based functional connections (n = 11). Using ML on fNIRS data might be a promising approach to reveal specific biomarkers for diagnostic classification.

Mental workload classification using convolutional neural networks based on fNIRS-derived prefrontal activity

BACKGROUND

Functional near-infrared spectroscopy (fNIRS) is a tool to assess brain activity during cognitive testing. Despite its usefulness, its feasibility in assessing mental workload remains unclear. This study was to investigate the potential use of convolutional neural networks (CNNs) based on functional near-infrared spectroscopy (fNIRS)-derived signals to classify mental workload in individuals with mild cognitive impairment.

METHODS

Spatial images by constructing a statistical activation map from the prefrontal activity of 120 subjects with MCI performing three difficulty levels of the N-back task (0, 1, and 2-back) were used for CNNs. The CNNs were evaluated using a 5 and 10-fold cross-validation method.

RESULTS

As the difficulty level of the N-back task increased, the accuracy decreased and prefrontal activity increased. In addition, there was a significant difference in the accuracy and prefrontal activity across the three levels (p's < 0.05). The accuracy of the CNNs based on fNIRS-derived spatial images evaluated by 5 and 10-fold cross-validation in classifying the difficulty levels ranged from 0.83 to 0.96.

CONCLUSION

fNIRS could also be a promising tool for measuring mental workload in older adults with MCI despite their cognitive decline. In addition, this study demonstrated the feasibility of the classification performance of the CNNs based on fNIRS-derived signals from the prefrontal cortex.

Effectiveness assessment of repetitive transcranial alternating current stimulation with concurrent EEG and fNIRS measurement

Transcranial alternating current stimulation (tACS) exhibits the capability to interact with endogenous brain oscillations using an external low-intensity sinusoidal current and influences cerebral function. Despite its potential benefits, the physiological mechanisms and effectiveness of tACS are currently a subject of debate and disagreement. The aims of our study are to (i) evaluate the neurological and behavioral impact of tACS by conducting repetitive sham-controlled experiments and (ii) propose criteria to evaluate effectiveness, which can serve as a benchmark to determine optimal individual-based tACS protocols. In this study, 15 healthy adults participated in the experiment over two visiting: sham and tACS (i.e., 5 Hz, 1 mA). During each visit, we used multimodal recordings of the participants' brain, including simultaneous electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS), along with a working memory (WM) score to quantify neurological effects and cognitive changes immediately after each repetitive sham/tACS session. Our results indicate increased WM scores, hemodynamic response strength, and EEG power in theta and delta bands both during and after the tACS period. Additionally, the observed effects do not increase with prolonged stimulation time, as the effects plateau towards the end of the experiment. In conclusion, our proposed closed-loop scheme offers a promising advance for evaluating the effectiveness of tACS during the stimulation session. Specifically, the assessment criteria use participant-specific brain-based signals along with a behavioral output. Moreover, we propose a feedback efficacy score that can aid in determining the optimal stimulation duration based on a participant-specific brain state, thereby preventing the risk of overstimulation.

Lateralization difference in functional activity during Stroop tasks: a functional near-infrared spectroscopy and EEG simultaneous study

Introduction

Conflict monitoring and processing is an important part of the human cognitive system, it plays a key role in many studies of cognitive disorders.

Methods

Based on a Chinese word-color match Stroop task, which included incongruent and neutral stimuli, the Electroencephalogram (EEG) and functional Near-infrared Spectroscopy (fNIRS) signals were recorded simultaneously. The Pearson correlation coefficient matrix was calculated to analyze brain connectivity based on EEG signals. Granger Causality (GC) method was employed to analyze the effective connectivity of bilateral frontal lobes. Wavelet Transform Coherence (WTC) was used to analyze the functional connectivity of the bilateral hemisphere and ipsilateral hemisphere.

Results

Results indicated that brain connectivity analysis on EEG signals did not show any significant lateralization, while fNIRS analysis results showed the frontal lobes especially the left frontal lobe play the leading role in dealing with conflict tasks. The human brain shows leftward lateralization while processing the more complicated incongruent stimuli. This is demonstrated by the higher functional connectivity in the left frontal lobe and the information flow from the left frontal lobe to the right frontal lobe.

Discussion

Our findings in brain connectivity during cognitive conflict processing demonstrated that the dual modality method combining EEG and fNIRS is a valuable tool to excavate more information through cognitive and physiological studies.

An Isolated CNN Architecture for Classification of Finger-Tapping Tasks Using Initial Dip Images: A Functional Near-Infrared Spectroscopy Study

This work investigates the classification of finger-tapping task images constructed for the initial dip duration of hemodynamics (HR) associated with the small brain area of the left motor cortex using functional near-infrared spectroscopy (fNIRS). Different layers (i.e., 16-layers, 19-layers, 22-layers, and 25-layers) of isolated convolutional neural network (CNN) designed from scratch are tested to classify the right-hand thumb and little finger-tapping tasks. Functional t-maps of finger-tapping tasks (thumb, little) were constructed for various durations (0.5 to 4 s with a uniform interval of 0.5 s) for the initial dip duration using a three gamma functions-based designed HR function. The results show that the 22-layered isolated CNN model yielded the highest classification accuracy of 89.2% with less complexity in classifying the functional t-maps of thumb and little fingers associated with the same small brain area using the initial dip. The results further demonstrated that the active brain area of the two tapping tasks from the same small brain area are highly different and well classified using functional t-maps of the initial dip (0.5 to 4 s) compared to functional t-maps generated for delayed HR (14 s). This study shows that the images constructed for initial dip duration can be helpful in the future for fNIRS-based diagnosis or cortical analysis of abnormal cerebral oxygen exchange in patients.

Illuminating neurodegeneration: a future perspective on near-infrared spectroscopy in dementia research

SIGNIFICANCE

Dementia presents a global healthcare crisis, and neuroimaging is the main method for developing effective diagnoses and treatments. Yet currently, there is a lack of sensitive, portable, and low-cost neuroimaging tools. As dementia is associated with vascular and metabolic dysfunction, near-infrared spectroscopy (NIRS) has the potential to fill this gap.

AIM

This future perspective aims to briefly review the use of NIRS in dementia to date and identify the challenges involved in realizing the full impact of NIRS for dementia research, including device development, study design, and data analysis approaches.

APPROACH

We briefly appraised the current literature to assess the challenges, giving a critical analysis of the methods used. To assess the sensitivity of different NIRS device configurations to the brain with atrophy (as is common in most forms of dementia), we performed an optical modeling analysis to compare their cortical sensitivity.

RESULTS

The first NIRS dementia study was published in 1996, and the number of studies has increased over time. In general, these studies identified diminished hemodynamic responses in the frontal lobe and altered functional connectivity in dementia. Our analysis showed that traditional (low-density) NIRS arrays are sensitive to the brain with atrophy (although we see a mean decrease of 22% in the relative brain sensitivity with respect to the healthy brain), but there is a significant improvement (a factor of 50 sensitivity increase) with high-density arrays.

CONCLUSIONS

NIRS has a bright future in dementia research. Advances in technology - high-density devices and intelligent data analysis-will allow new, naturalistic task designs that may have more clinical relevance and increased reproducibility for longitudinal studies. The portable and low-cost nature of NIRS provides the potential for use in clinical and screening tests.

System Derived Spatial-Temporal CNN for High-Density fNIRS BCI

An intuitive and generalisable approach to spatial-temporal feature extraction for high-density (HD) functional Near-Infrared Spectroscopy (fNIRS) brain-computer interface (BCI) is proposed, demonstrated here using Frequency-Domain (FD) fNIRS for motor-task classification. Enabled by the HD probe design, layered topographical maps of Oxy/deOxy Haemoglobin changes are used to train a 3D convolutional neural network (CNN), enabling simultaneous extraction of spatial and temporal features. The proposed spatial-temporal CNN is shown to effectively exploit the spatial relationships in HD fNIRS measurements to improve the classification of the functional haemodynamic response, achieving an average F1 score of 0.69 across seven subjects in a mixed subjects training scheme, and improving subject-independent classification as compared to a standard temporal CNN.

Comparing Multi-Dimensional fNIRS Features Using Bayesian Optimization-Based Neural Networks for Mild Cognitive Impairment (MCI) Detection

The diagnosis of mild cognitive impairment (MCI), a prodromal stage of Alzheimer's disease (AD), is essential for initiating timely treatment to delay the onset of AD. Previous studies have shown the potential of functional near-infrared spectroscopy (fNIRS) for diagnosing MCI. However, preprocessing fNIRS measurements requires extensive experience to identify poor-quality segments. Moreover, few studies have explored how proper multi-dimensional fNIRS features influence the classification results of the disease. Thus, this study outlined a streamlined fNIRS preprocessing method to process fNIRS measurements and compared multi-dimensional fNIRS features with neural networks in order to explore how temporal and spatial factors affect the classification of MCI and cognitive normality. More specifically, this study proposed using Bayesian optimization-based auto hyperparameter tuning neural networks to evaluate 1D channel-wise, 2D spatial, and 3D spatiotemporal features of fNIRS measurements for detecting MCI patients. The highest test accuracies of 70.83%, 76.92%, and 80.77% were achieved for 1D, 2D, and 3D features, respectively. Through extensive comparisons, the 3D time-point oxyhemoglobin feature was proven to be a more promising fNIRS feature for detecting MCI by using an fNIRS dataset of 127 participants. Furthermore, this study presented a potential approach for fNIRS data processing, and the designed models required no manual hyperparameter tuning, which promoted the general utilization of fNIRS modality with neural network-based classification to detect MCI.

Transcranial direct current stimulation for the treatment of post-stroke depression: A systematic review

Background

Post-stroke depression (PSD) is not only a frequent neuropsychiatric manifestation secondary to stroke but is also associated with disability, poor rehabilitation outcomes, sleep disorders, cognitive impairment, and increased mortality. Transcranial direct current stimulation (tDCS), a primary modality of non-invasive brain stimulation (NIBS), has shown promising clinical results in the rehabilitation of patients with PSD recently. The primary aim of this systematic review is to assess the effects of tDCS on PSD.

Methods

PubMed and Cochrane databases were used for paper identification up to May 2022. Only English language studies and published data were taken into consideration. The methodological quality of selected studies was assessed according to the modified Sackett Scale, based on Physiotherapy Evidence Database (PEDro) scores.

Results

Six experimental studies were included for the PSD treatment of tDCS and all of them reported that, following the intervention of tDCS, the experimental group shows a statistically significant decrease in the depression level in accordance with different assessment scales.

Conclusion

This article simply aims at providing a comprehensive overview of the raw data reported in this field to date. Based on the current evidence, tDCS presents promising results for the treatment of PSD. Moreover, tDCS is also effective in PSD patients with aphasia or CPSP. However, an optimal stimulation protocol is needed to formulate. Thus, the development of robustly controlled, randomized, and high-quality clinical trials to further assess the utility of tDCS as a therapeutic tool for the treatment of PSD survivors is encouraged.

Systematic review registration

https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42023322076, identifier: CRD42023322076.

fNIRS-based brain functional response to robot-assisted training for upper-limb in stroke patients with hemiplegia

Background

Robot-assisted therapy (RAT) has received considerable attention in stroke motor rehabilitation. Characteristics of brain functional response associated with RAT would provide a theoretical basis for choosing the appropriate protocol for a patient. However, the cortical response induced by RAT remains to be fully elucidated due to the lack of dynamic brain functional assessment tools.

Objective

To guide the implementation of clinical therapy, this study focused on the brain functional responses induced by RAT in patients with different degrees of motor impairment.

Methods

A total of 32 stroke patients were classified into a low score group (severe impairment, n = 16) and a high score group (moderate impairment, n = 16) according to the motor function of the upper limb and then underwent RAT training in assistive mode with simultaneous cerebral haemodynamic measurement by functional near-infrared spectroscopy (fNIRS). Functional connectivity (FC) and the hemisphere autonomy index (HAI) were calculated based on the wavelet phase coherence among fNIRS signals covering bilateral prefrontal, motor and occipital areas.

Results

Specific cortical network response related to RAT was observed in patients with unilateral moderate-to-severe motor deficits in the subacute stage. Compared with patients with moderate dysfunction, patients with severe impairment showed a wide range of significant FC responses in the bilateral hemispheres induced by RAT with the assistive mode, especially task-related involvement of ipsilesional supplementary motor areas.

Conclusion

Under assisted mode, RAT-related extensive cortical response in patients with severe dysfunction might contribute to brain functional organization during motor performance, which is considered the basic neural substrate of motor-related processes. In contrast, the limited cortical response related to RAT in patients with moderate dysfunction may indicate that the training intensity needs to be adjusted in time according to the brain functional state. fNIRS-based assessment of brain functional response assumes great importance for the customization of an appropriate protocol training in the clinical practice.

Programming ability prediction: Applying an attention-based convolutional neural network to functional near-infrared spectroscopy analyses of working memory

Although theoretical studies have suggested that working-memory capacity is crucial for academic achievement, few empirical studies have directly investigated the relationship between working-memory capacity and programming ability, and no direct neural evidence has been reported to support this relationship. The present study aimed to fill this gap in the literature. Using a between-subject design, 17 programming novices and 18 advanced students performed an n-back working-memory task. During the experiment, their prefrontal hemodynamic responses were measured using a 48-channel functional near-infrared spectroscopy (fNIRS) device. The results indicated that the advanced students had a higher working-memory capacity than the novice students, validating the relationship between programming ability and working memory. The analysis results also showed that the hemodynamic responses in the prefrontal cortex can be used to discriminate between novices and advanced students. Additionally, we utilized an attention-based convolutional neural network to analyze the spatial domains of the fNIRS signals and demonstrated that the left prefrontal cortex was more important than other brain regions for programming ability prediction. This result was consistent with the results of statistical analysis, which in turn improved the interpretability of neural networks.

Use of Hypoxic Respiratory Challenge for Differentiating Alzheimer's Disease and Wild-Type Mice Non-Invasively: A Diffuse Optical Spectroscopy Study

Alzheimer's disease is one of the most critical brain diseases. The prevalence of the disease keeps rising due to increasing life spans. This study aims to examine the use of hemodynamic signals during hypoxic respiratory challenge for the differentiation of Alzheimer's disease (AD) and wild-type (WT) mice. Diffuse optical spectroscopy, an optical system that can non-invasively monitor transient changes in deoxygenated (ΔRHb) and oxygenated (ΔOHb) hemoglobin concentrations, was used to monitor hemodynamic reactivity during hypoxic respiratory challenges in an animal model. From the acquired signals, 13 hemodynamic features were extracted from each of ΔRHb and -ΔOHb (26 features total) for more in-depth analyses of the differences between AD and WT. The hemodynamic features were statistically analyzed and tested to explore the possibility of using machine learning (ML) to differentiate AD and WT. Among the twenty-six features, two features of ΔRHb and one feature of -ΔOHb showed statistically significant differences between AD and WT. Among ML techniques, a naive Bayes algorithm achieved the best accuracy of 84.3% when whole hemodynamic features were used for differentiation. While further works are required to improve the approach, the suggested approach has the potential to be an alternative method for the differentiation of AD and WT.

Deep learning in fNIRS: a review

Significance: Optical neuroimaging has become a well-established clinical and research tool to monitor cortical activations in the human brain. It is notable that outcomes of functional near-infrared spectroscopy (fNIRS) studies depend heavily on the data processing pipeline and classification model employed. Recently, deep learning (DL) methodologies have demonstrated fast and accurate performances in data processing and classification tasks across many biomedical fields. Aim: We aim to review the emerging DL applications in fNIRS studies. Approach: We first introduce some of the commonly used DL techniques. Then, the review summarizes current DL work in some of the most active areas of this field, including brain-computer interface, neuro-impairment diagnosis, and neuroscience discovery. Results: Of the 63 papers considered in this review, 32 report a comparative study of DL techniques to traditional machine learning techniques where 26 have been shown outperforming the latter in terms of the classification accuracy. In addition, eight studies also utilize DL to reduce the amount of preprocessing typically done with fNIRS data or increase the amount of data via data augmentation. Conclusions: The application of DL techniques to fNIRS studies has shown to mitigate many of the hurdles present in fNIRS studies such as lengthy data preprocessing or small sample sizes while achieving comparable or improved classification accuracy.

Neuroimaging Modalities in Alzheimer's Disease: Diagnosis and Clinical Features

Alzheimer's disease (AD) is a neurodegenerative disease causing progressive cognitive decline until eventual death. AD affects millions of individuals worldwide in the absence of effective treatment options, and its clinical causes are still uncertain. The onset of dementia symptoms indicates severe neurodegeneration has already taken place. Therefore, AD diagnosis at an early stage is essential as it results in more effective therapy to slow its progression. The current clinical diagnosis of AD relies on mental examinations and brain imaging to determine whether patients meet diagnostic criteria, and biomedical research focuses on finding associated biomarkers by using neuroimaging techniques. Multiple clinical brain imaging modalities emerged as potential techniques to study AD, showing a range of capacity in their preciseness to identify the disease. This review presents the advantages and limitations of brain imaging modalities for AD diagnosis and discusses their clinical value.

Deep Learning-Based Multilevel Classification of Alzheimer’s Disease Using Non-invasive Functional Near-Infrared Spectroscopy

The timely diagnosis of Alzheimer’s disease (AD) and its prodromal stages is critically important for the patients, who manifest different neurodegenerative severity and progression risks, to take intervention and early symptomatic treatments before the brain damage is shaped. As one of the promising techniques, functional near-infrared spectroscopy (fNIRS) has been widely employed to support early-stage AD diagnosis. This study aims to validate the capability of fNIRS coupled with Deep Learning (DL) models for AD multi-class classification. First, a comprehensive experimental design, including the resting, cognitive, memory, and verbal tasks was conducted. Second, to precisely evaluate the AD progression, we thoroughly examined the change of hemodynamic responses measured in the prefrontal cortex among four subject groups and among genders. Then, we adopted a set of DL architectures on an extremely imbalanced fNIRS dataset. The results indicated that the statistical difference between subject groups did exist during memory and verbal tasks. This presented the correlation of the level of hemoglobin activation and the degree of AD severity. There was also a gender effect on the hemoglobin changes due to the functional stimulation in our study. Moreover, we demonstrated the potential of distinguished DL models, which boosted the multi-class classification performance. The highest accuracy was achieved by Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) using the original dataset of three hemoglobin types (0.909 ± 0.012 on average). Compared to conventional machine learning algorithms, DL models produced a better classification performance. These findings demonstrated the capability of DL frameworks on the imbalanced class distribution analysis and validated the great potential of fNIRS-based approaches to be further contributed to the development of AD diagnosis systems.

Diagnosis of Mild Cognitive Impairment with Ordinal Pattern Kernel

Mild cognitive impairment (MCI) belongs to the prodromal stage of Alzheimer's disease (AD). Accurate diagnosis of MCI is very important for possibly deferring AD progression. Graph kernels, which measure the similarity between paired brain connectivity networks, have been widely used to diagnose brain diseases (e.g., MCI) and yielded promising classification performance. However, most of the existing graph kernels are based on unweighted graphs, and neglect the valuable weighted information of the edges in brain connectivity networks where edge weights convey the strengths of fiber connection or temporal correlation between paired brain regions. Accordingly, in this paper, we propose a new graph kernel called ordinal pattern kernel for measuring brain connectivity network similarity and apply it to brain disease classification tasks. Different from the existing graph kernels which measure the topological similarity of the unweighted graphs, our proposed ordinal pattern kernel can not only calculate the similarity of paired brain connectivity networks, but also capture the ordinal pattern relationship of edge weights in brain connectivity networks. To appraise the effectiveness of our proposed method, we perform extensive experiments in functional magnetic resonance imaging data of brain disease from Alzheimer's Disease Neuroimaging Initiative database. The experimental results show that our proposed ordinal pattern kernel outperforms the state-of-the-art graph kernels in the classification tasks of MCI.

Applications of artificial intelligence to aid early detection of dementia: A scoping review on current capabilities and future directions

BACKGROUND & OBJECTIVE

With populations aging, the number of people with dementia worldwide is expected to triple to 152 million by 2050. Seventy percent of cases are due to Alzheimer's disease (AD) pathology and there is a 10-20 year 'pre-clinical' period before significant cognitive decline occurs. We urgently need, cost effective, objective biomarkers to detect AD, and other dementias, at an early stage. Risk factor modification could prevent 40% of cases and drug trials would have greater chances of success if participants are recruited at an earlier stage. Currently, detection of dementia is largely by pen and paper cognitive tests but these are time consuming and insensitive to the pre-clinical phase. Specialist brain scans and body fluid biomarkers can detect the earliest stages of dementia but are too invasive or expensive for widespread use. With the advancement of technology, Artificial Intelligence (AI) shows promising results in assisting with detection of early-stage dementia. This scoping review aims to summarise the current capabilities of AI-aided digital biomarkers to aid in early detection of dementia, and also discusses potential future research directions.

METHODS & MATERIALS

In this scoping review, we used PubMed and IEEE Xplore to identify relevant papers. The resulting records were further filtered to retrieve articles published within five years and written in English. Duplicates were removed, titles and abstracts were screened and full texts were reviewed.

RESULTS

After an initial yield of 1,463 records, 1,444 records were screened after removal of duplication. A further 771 records were excluded after screening titles and abstracts, and 496 were excluded after full text review. The final yield was 177 studies. Records were grouped into different artificial intelligence based tests: (a) computerized cognitive tests (b) movement tests (c) speech, conversion, and language tests and (d) computer-assisted interpretation of brain scans.

CONCLUSIONS

In general, AI techniques enhance the performance of dementia screening tests because more features can be retrieved from a single test, there are less errors due to subjective judgements and AI shifts the automation of dementia screening to a higher level. Compared with traditional cognitive tests, AI-based computerized cognitive tests improve the discrimination sensitivity by around 4% and specificity by around 3%. In terms of speech, conversation and language tests, combining both acoustic features and linguistic features achieve the best result with accuracy around 94%. Deep learning techniques applied in brain scan analysis achieves around 92% accuracy. Movement tests and setting smart environments to capture daily life behaviours are two potential future directions that may help discriminate dementia from normal aging. AI-based smart environments and multi-modal tests are promising future directions to improve detection of dementia in the earliest stages.

Identification of ∆9-tetrahydrocannabinol (THC) impairment using functional brain imaging

The primary cannabinoid in cannabis, Δ9-tetrahydrocannabinol (THC), causes intoxication and impaired function, with implications for traffic, workplace, and other situational safety risks. There are currently no evidence-based methods to detect cannabis-impaired driving, and current field sobriety tests with gold-standard, drug recognition evaluations are resource-intensive and may be prone to bias. This study evaluated the capability of a simple, portable imaging method to accurately detect individuals with THC impairment. In this double-blind, randomized, cross-over study, 169 cannabis users, aged 18-55 years, underwent functional near-infrared spectroscopy (fNIRS) before and after receiving oral THC and placebo, at study visits one week apart. Impairment was defined by convergent classification by consensus clinical ratings and an algorithm based on post-dose tachycardia and self-rated "high." Our primary outcome, prefrontal cortex (PFC) oxygenated hemoglobin concentration (HbO), was increased after THC only in participants operationalized as impaired, independent of THC dose. ML models using fNIRS time course features and connectivity matrices identified impairment with 76.4% accuracy, 69.8% positive predictive value (PPV), and 10% false-positive rate using convergent classification as ground truth, which exceeded Drug Recognition Evaluator-conducted expanded field sobriety examination (67.8% accuracy, 35.4% PPV, and 35.4% false-positive rate). These findings demonstrate that PFC response activation patterns and connectivity produce a neural signature of impairment, and that PFC signal, measured with fNIRS, can be used as a sole input to ML models to objectively determine impairment from THC intoxication at the individual level. Future work is warranted to determine the specificity of this classifier to acute THC impairment.ClinicalTrials.gov Identifier: NCT03655717.

Refined prefrontal working memory network as a neuromarker for Alzheimer's disease

Detecting Alzheimer's disease (AD) is an important step in preventing pathological brain damage. Working memory (WM)-related network modulation can be a pathological feature of AD, but is usually modulated by untargeted cognitive processes and individual variance, resulting in the concealment of this key information. Therefore, in this study, we comprehensively investigated a new neuromarker, named "refined network," in a prefrontal cortex (PFC) that revealed the pathological features of AD. A refined network was acquired by removing unnecessary variance from the WM-related network. By using a functional near-infrared spectroscopy (fNIRS) device, we evaluated the reliability of the refined network, which was identified from the three groups classified by AD progression: healthy people (N=31), mild cognitive impairment (N=11), and patients with AD (N=18). As a result, we identified edges with significant correlations between cognitive functions and groups in the dorsolateral PFC. Moreover, the refined network achieved a significantly correlating metric with neuropsychological test scores, and a remarkable three-class classification accuracy (95.0%). These results implicate the refined PFC WM-related network as a powerful neuromarker for AD screening.

fNIRS-derived neurocognitive ratio as a biomarker for neuropsychiatric diseases

Significance: Clinical use of fNIRS-derived features has always suffered low sensitivity and specificity due to signal contamination from background systemic physiological fluctuations. We provide an algorithm to extract cognition-related features by eliminating the effect of background signal contamination, hence improving the classification accuracy. Aim: The aim in this study is to investigate the classification accuracy of an fNIRS-derived biomarker based on global efficiency (GE). To this end, fNIRS data were collected during a computerized Stroop task from healthy controls and patients with migraine, obsessive compulsive disorder, and schizophrenia. Approach: Functional connectivity (FC) maps were computed from [HbO] time series data for neutral (N), congruent (C), and incongruent (I) stimuli using the partial correlation approach. Reconstruction of FC matrices with optimal choice of principal components yielded two independent networks: cognitive mode network (CM) and default mode network (DM). Results: GE values computed for each FC matrix after applying principal component analysis (PCA) yielded strong statistical significance leading to a higher specificity and accuracy. A new index, neurocognitive ratio (NCR), was computed by multiplying the cognitive quotients (CQ) and ratio of GE of CM to GE of DM. When mean values of NCR ( N C R ¯ ) over all stimuli were computed, they showed high sensitivity (100%), specificity (95.5%), and accuracy (96.3%) for all subjects groups. Conclusions: N C R ¯ can reliable be used as a biomarker to improve the classification of healthy to neuropsychiatric patients.

Recognition of Flexion and Extension Imagery Involving the Right and Left Arms Based on Deep Belief Network and Functional Near-Infrared Spectroscopy

Brain-computer interaction based on motor imagery (MI) is an important brain-computer interface (BCI). Most methods for MI classification are based on electroencephalogram (EEG), and few studies have investigated signal processing based on MI-Functional Near-Infrared Spectroscopy (fNIRS). In addition, there is a need to improve the classification accuracy for MI fNIRS methods. In this study, a deep belief network (DBN) based on a restricted Boltzmann machine (RBM) was used to classify fNIRS signals of flexion and extension imagery involving the left and right arms. fNIRS signals from 16 channels covering the motor cortex area were recorded for each of 10 subjects executing or imagining flexion and extension involving the left and right arms. Oxygenated hemoglobin (HbO) concentration was used as a feature to train two RBMs that were subsequently stacked with an additional softmax regression output layer to construct DBN. We also explored the DBN model classification accuracy for the test dataset from one subject using training dataset from other subjects. The average DBN classification accuracy for flexion and extension movement and imagery involving the left and right arms was 84.35 ± 3.86% and 78.19 ± 3.73%, respectively. For a given DBN model, better classification results are obtained for test datasets for a given subject when the model is trained using dataset from the same subject than when the model is trained using datasets from other subjects. The results show that the DBN algorithm can effectively identify flexion and extension imagery involving the right and left arms using fNIRS. This study is expected to serve as a reference for constructing online MI-BCI systems based on DBN and fNIRS.

Decoding Multiple Sound-Categories in the Auditory Cortex by Neural Networks: An fNIRS Study

This study aims to decode the hemodynamic responses (HRs) evoked by multiple sound-categories using functional near-infrared spectroscopy (fNIRS). The six different sounds were given as stimuli (English, non-English, annoying, nature, music, and gunshot). The oxy-hemoglobin (HbO) concentration changes are measured in both hemispheres of the auditory cortex while 18 healthy subjects listen to 10-s blocks of six sound-categories. Long short-term memory (LSTM) networks were used as a classifier. The classification accuracy was 20.38 ± 4.63% with six class classification. Though LSTM networks' performance was a little higher than chance levels, it is noteworthy that we could classify the data subject-wise without feature selections.

Systemic Review on Transcranial Electrical Stimulation Parameters and EEG/fNIRS Features for Brain Diseases

Background

Brain disorders are gradually becoming the leading cause of death worldwide. However, the lack of knowledge of brain disease’s underlying mechanisms and ineffective neuropharmacological therapy have led to further exploration of optimal treatments and brain monitoring techniques.

Objective

This study aims to review the current state of brain disorders, which utilize transcranial electrical stimulation (tES) and daily usable noninvasive neuroimaging techniques. Furthermore, the second goal of this study is to highlight available gaps and provide a comprehensive guideline for further investigation.

Method

A systematic search was conducted of the PubMed and Web of Science databases from January 2000 to October 2020 using relevant keywords. Electroencephalography (EEG) and functional near-infrared spectroscopy were selected as noninvasive neuroimaging modalities. Nine brain disorders were investigated in this study, including Alzheimer’s disease, depression, autism spectrum disorder, attention-deficit hyperactivity disorder, epilepsy, Parkinson’s disease, stroke, schizophrenia, and traumatic brain injury.

Results

Sixty-seven studies (1,385 participants) were included for quantitative analysis. Most of the articles (82.6%) employed transcranial direct current stimulation as an intervention method with modulation parameters of 1 mA intensity (47.2%) for 16–20 min (69.0%) duration of stimulation in a single session (36.8%). The frontal cortex (46.4%) and the cerebral cortex (47.8%) were used as a neuroimaging modality, with the power spectrum (45.7%) commonly extracted as a quantitative EEG feature.

Conclusion

An appropriate stimulation protocol applying tES as a therapy could be an effective treatment for cognitive and neurological brain disorders. However, the optimal tES criteria have not been defined; they vary across persons and disease types. Therefore, future work needs to investigate a closed-loop tES with monitoring by neuroimaging techniques to achieve personalized therapy for brain disorders.

Quantitative Assessment of Resting-State for Mild Cognitive Impairment Detection: A Functional Near-Infrared Spectroscopy and Deep Learning Approach

BACKGROUND

Mild cognitive impairment (MCI) is considered a prodromal stage of Alzheimer's disease. Early diagnosis of MCI can allow for treatment to improve cognitive function and reduce modifiable risk factors.

OBJECTIVE

This study aims to investigate the feasibility of individual MCI detection from healthy control (HC) using a minimum duration of resting-state functional near-infrared spectroscopy (fNIRS) signals.

METHODS

In this study, nine different measurement durations (i.e., 30, 60, 90, 120, 150, 180, 210, 240, and 270 s) were evaluated for MCI detection via the graph theory analysis and traditional machine learning approach, such as linear discriminant analysis, support vector machine, and K-nearest neighbor algorithms. Moreover, feature representation- and classification-based transfer learning (TL) methods were applied to identify MCI from HC through the input of connectivity maps with 30 and 90 s duration.

RESULTS

There was no significant difference among the nine various time windows in the machine learning and graph theory analysis. The feature representation-based TL showed improved accuracy in both 30 and 90 s cases (i.e., 30 s: 81.27% and 90 s: 76.73%). Notably, the classification-based TL method achieved the highest accuracy of 95.81% using the pre-trained convolutional neural network (CNN) model with the 30 s interval functional connectivity map input.

CONCLUSION

The results indicate that a 30 s measurement of the resting-state with fNIRS could be used to detect MCI. Moreover, the combination of neuroimaging (e.g., functional connectivity maps) and deep learning methods (e.g., CNN and TL) can be considered as novel biomarkers for clinical computer-assisted MCI diagnosis.

Activation of Prefrontal Cortex in Process of Oral and Finger Shape Discrimination: fNIRS Study

Background

The differences in the brain activities of the insular and the visual association cortices have been reported between oral and manual stereognosis. However, these results were not conclusive because of the inherent differences in the task performance-related motor sequence conditions. We hypothesized that the involvement of the prefrontal cortex may be different between finger and oral shape discrimination. This study was conducted to clarify temporal changes in prefrontal activities occurring in the processes of oral and finger tactual shape discrimination using prefrontal functional near-infrared spectroscopy (fNIRS).

Methods

Six healthy right-handed males [aged 30.8 ± 8.2 years (mean ± SD)] were enrolled. Measurements of prefrontal activities were performed using a 22-channel fNIRS device (ETG-100, Hitachi Medical Co., Chiba, Japan) during experimental blocks that included resting state (REST), nonsense shape discrimination (SHAM), and shape discrimination (SHAPE).

Results

No significant difference was presented with regard to the number of correct answers during trials between oral and finger SHAPE discrimination. Additionally, a statistical difference for the prefrontal fNIRS activity between oral and finger shape discrimination was noted in CH 1. Finger SHAPE, as compared with SHAM, presented a temporally shifting onset and burst in the prefrontal activities from the frontopolar area (FPA) to the orbitofrontal cortex (OFC). In contrast, oral SHAPE as compared with SHAM was shown to be temporally overlapped in the onset and burst of the prefrontal activities in the dorsolateral prefrontal cortex (DLPFC)/FPA/OFC.

Conclusion

The prefrontal activities temporally shifting from the FPA to the OFC during SHAPE as compared with SHAM may suggest the segregated serial prefrontal processing from the manipulation of a target image to the decision making during the process of finger shape discrimination. In contrast, the temporally overlapped prefrontal activities of the DLPFC/FPA/OFC in the oral SHAPE block may suggest the parallel procession of the repetitive involvement of generation, manipulation, and decision making in order to form a reliable representation of target objects.

A Bipolar-Channel Hybrid Brain-Computer Interface System for Home Automation Control Utilizing Steady-State Visually Evoked Potential and Eye-Blink Signals

The goal of this study was to develop and validate a hybrid brain-computer interface (BCI) system for home automation control. Over the past decade, BCIs represent a promising possibility in the field of medical (e.g., neuronal rehabilitation), educational, mind reading, and remote communication. However, BCI is still difficult to use in daily life because of the challenges of the unfriendly head device, lower classification accuracy, high cost, and complex operation. In this study, we propose a hybrid BCI system for home automation control with two brain signals acquiring electrodes and simple tasks, which only requires the subject to focus on the stimulus and eye blink. The stimulus is utilized to select commands by generating steady-state visually evoked potential (SSVEP). The single eye blinks (i.e., confirm the selection) and double eye blinks (i.e., deny and re-selection) are employed to calibrate the SSVEP command. Besides that, the short-time Fourier transform and convolution neural network algorithms are utilized for feature extraction and classification, respectively. The results show that the proposed system could provide 38 control commands with a 2 s time window and a good accuracy (i.e., 96.92%) using one bipolar electroencephalogram (EEG) channel. This work presents a novel BCI approach for the home automation application based on SSVEP and eye blink signals, which could be useful for the disabled. In addition, the provided strategy of this study—a friendly channel configuration (i.e., one bipolar EEG channel), high accuracy, multiple commands, and short response time—might also offer a reference for the other BCI controlled applications.